© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108642
    Prev
    Next
    INDEX
    Explanations

    geographical prepositions and directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igator
    -0.07
    regor
    -0.07
    ukan
    -0.06
    inputEmail
    -0.06
    ximity
    -0.06
    apiro
    -0.06
    leine
    -0.06
    -Americ
    -0.06
    verbatim
    -0.06
    855
    -0.06
    POSITIVE LOGITS
     Ana
    0.07
    ког
    0.06
    OLL
    0.06
    ç¿°
    0.06
    ικο
    0.06
     Hearth
    0.06
    oll
    0.06
    öt
    0.06
     ana
    0.06
    ëįķ
    0.06
    Activations Density 0.004%

    No Known Activations